Remote AI Research Engineer: Multimodal Quantization

Tether Operations Limited; United States; À distance; EUR 90 000 - 150 000; Plein temps

Résumé du poste

Tether Operations Limited is seeking an AI research engineer to advance model compression for multimodal AI, targeting edge devices and efficient deployment of LLMs and VLMs.

You will apply quantization, distillation, and pruning, publish findings at top conferences, and collaborate with a global team of researchers.

A PhD is preferred; strong PyTorch experience is required; familiarity with C++ is a plus.

Qualifications

• PhD in NLP/ ML (preferred).

Responsabilités

• Apply low‑bit quantization to reduce model size and latency.
• Leverage knowledge distillation to transfer capabilities from larger models.
• Implement pruning to remove redundant parameters and attention heads.
• Analyze trade‑offs between efficiency and accuracy across methods.
• Research mixed‑precision quantization and adaptive pruning schedules.
• Stay current with multimodal AI compression research.
• Document methodologies and results for reproducibility.
• Publish findings in top conferences (NeurIPS, ICML, ICLR, CVPR, ACL, AAAI).

Connaissances

Model compression

Multimodal AI

Knowledge distillation

Quantization

Pruning

Transformers

Edge deployment

Inference optimization

Formation

Degree in Computer Science or related field

PhD in NLP/ML (preferred)

Outils

PyTorch

C++

Description du poste

Tether Operations Limited is seeking an AI research engineer to advance model compression for multimodal AI, targeting edge devices and efficient deployment of LLMs and VLMs.

You will apply quantization, distillation, and pruning, publish findings at top conferences, and collaborate with a global team of researchers.

A PhD is preferred; strong PyTorch experience is required; familiarity with C++ is a plus.